Regio- and Stereoselective Steroid Hydroxylation at C7 by Cytochrome†P450 Monooxygenase Mutants.

Steroidal C7ß alcohols and their respective esters have shown significant promise as neuroprotective and anti-inflammatory agents to treat chronic neuronal damage like stroke, brain trauma, and cerebral ischemia. Since C7 is spatially far away from any functional groups that could direct C-H activation, these transformations are not readily accessible using modern synthetic organic techniques. Reported here are P450-BM3 mutants that catalyze the oxidative hydroxylation of six different steroids with pronounced C7 regioselectivities and ß stereoselectivities, as well as high activities. These challenging transformations were achieved by a focused mutagenesis strategy and application of a novel technology for protein library construction based on DNA assembly and USER (Uracil-Specific Excision Reagent) cloning. Upscaling reactions enabled the purification of the respective steroidal alcohols in moderate to excellent yields. The high-resolution X-ray structure and molecular dynamics simulations of the best mutant unveil the origin of regio- and stereoselectivity.

Machine learning-driven protein engineering: a case study in computational drug discovery.

Research and development in drug discovery will need to find significant efficiency gains if the industry is to continue generating novel drugs. There is great expectation for machine learning (ML) to provide this boost in R&D productivity, but to harness the full potential of ML, the generation of new, high-quality datasets will be necessary. Here, the authors present a platform that combines high-throughput display and selection data generation with ML. More specifically, deep learning is used to inform the directed evolution of novel biotherapeutics using DNA library synthesis, ultra-high throughput selections, and next generation sequencing. By combining the learnings of multiple in silico models, their platform enables multi-parameter optimisation across multiple important protein characteristics. They also present a model for benchmarking these ML-driven drug discovery platforms according to the accuracy of their underlying in silico models, in conjunction with the throughput of their empirical experimentation.